Skip to content

Benchmark

RepoQA

Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.

Models measured
2
Scores recorded
3
Sources
2
IQ weight
No weight published

Score distribution

87.4%
Mean
88.5%
Median
1.7%
Std dev
85%
10th percentile
88.7%
90th percentile
85%
Min
85%88.7%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Step 3.5 FlashStep 3.5 technical report · Table 5 · PaCoRe· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.88.7%
2Step 3.5 FlashStep 3.5 technical report · Table 5 · vanilla· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.88.5%
3phi-3.5-moe-instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85%

Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.